Kernel PCA for Type Ia supernovae photometric classification

  title={Kernel PCA for Type Ia supernovae photometric classification},
  author={Emille E. O. Ishida and Rafael S. de Souza},
  journal={Monthly Notices of the Royal Astronomical Society},
  • E. IshidaR. Souza
  • Published 31 January 2012
  • Physics, Computer Science
  • Monthly Notices of the Royal Astronomical Society
The problem of supernova photometric identication will be extremely important for large surveys in the next decade. In this work, we propose the use of Kernel Principal Component Analysis (KPCA) combined with k = 1 nearest neighbour algorithm (1NN) as a framework for supernovae (SNe) photometric classication. 

Improved KPCA for supernova photometric classification

It is demonstrated that the introduction of Gaussian Process Regression in determining each light curve highly improves the efficiency and purity rates, and is found to be satisfactorily efficient.

Photometric classification of Supernovae from the SUDARE survey

  • G. Pignata
  • Physics
    Proceedings of the International Astronomical Union
  • 2014
First results from the algorithm developed to photometrically classify the Supernovae discovered by the Supernova Diversity and Rate Evolution (SUDARE) are presented.

Photometric classification of type Ia supernovae in the SuperNova Legacy Survey with supervised learning

The feasibility of machine learning classification in a high-z SN survey with application to real SN data is demonstrated, and the differences between classifying simulated SNe, and real SN survey data are investigated.


We present a new photometric identification technique for SN 1991bg-like type Ia supernovae (SNe Ia), i.e., objects with light curve characteristics such as later primary maxima and the absence of a

Automated supernova Ia classification using adaptive learning techniques

This work presents an adaptive mechanism that generates a predictive model to identify a particular class of SN known as Type Ia, when the source set is made of spectroscopic data, while the target set ismade of photometric data.


A multi-faceted classification pipeline, combining existing and new approaches, finds that by using either the SALT2 or the wavelet feature sets with a BDT algorithm, accurate classification is possible purely from light curve data, without the need for any redshift information.

Exploring the spectroscopic diversity of type Ia supernovae with Deep Learning and Unsupervised Clustering

This work shows how machine learning tools facilitate identification of subtypes of SNe Ia using Deep Learning for dimensionality reduction, and shows evidence that the progenitor system and the explosion mechanism can be described with a small number of initial physical parameters.

Variability search in M 31 using principal component analysis and the Hubble Source Catalogue

Principal Component Analysis (PCA) is being extensively used in Astronomy but not yet exhaustively exploited for variability search. The aim of this work is to investigate the effectiveness of using

The application of automatic classification of massive SDSS spectra

A novel technique for automatically classifying massive stellar spectra selected from SDSS is presented and the result of the experiment indicates that the classification accuracy is up to 90% which proves the effectiveness of the method.

On the cosmological performance of photometrically classified supernovae with machine learning

This paper investigates the performance of machine learning (ML) classification on the final cosmological constraints using simulated lightcurves from The Supernova Photometric Classification Challenge, released in 2010, and proposes a threshold selection method to construct the final catalogs.



Bayesian Single-Epoch Photometric Classification of Supernovae

Ongoing supernova (SN) surveys find hundreds of candidates that require confirmation for their various uses. Traditional classification based on follow-up spectroscopy of all candidates is virtually

A Probabilistic Approach to Classifying Supernovae Using Photometric Information

This paper presents a novel method for determining the probability that a supernova candidate belongs to a known supernova type (such as Ia, Ibc, IIL, etc.) using its photometric information alone.

Semi-supervised learning for photometric supernova classification★

We present a semi-supervised method for photometric supernova typing. Our approach is to first use the non-linear dimension reduction technique diffusion map to detect structure in a data base of

Statistical classification techniques for photometric supernova typing

Future photometric supernova surveys will produce vastly more candidates than can be followed up spectroscopically, highlighting the need for effective classification methods based on light curves

Photometric Identification of Type Ia Supernovae at Moderate Redshift

Large photometric surveys with the aim of identifying many Type Ia supernovae (SNe) at moderate redshift are challenged in separating these SNe from other SN types. We are motivated to identify Type

Photometric Selection of High-Redshift Type Ia Supernova Candidates

We present a method for selecting high-redshift Type Ia supernovae (SNe Ia) located via rolling SN searches. The technique, using both color and magnitude information of events from only two to three


We analyze the three-year Sloan Digital Sky Survey II (SDSS-II) Supernova (SN) Survey data and identify a sample of 1070 photometric Type Ia supernova (SN Ia) candidates based on their multiband

A simple and robust method for automated photometric classification of supernovae using neural networks

A method is presented for automated photometric classificat ion of supernovae (SNe) as TypeIa or non-Ia. A two-step approach is adopted in which: (i) the SN lightcurve flux measurements in each

Results from the Supernova Photometric Classification Challenge

We report results from the Supernova Photometric Classification Challenge (SNPhotCC), a publicly released mix of simulated supernovae (SNe), with types (Ia, Ibc, and II) selected in proportion to


We discuss the extent to which photometric measurements alone can be used to identify Type Ia supernovae (SNIa) and to determine the redshift and other parameters of interest for cosmological